Triple
T4213997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salonika Expedition |
E93969
|
entity |
| Predicate | basedAround |
P20207
|
FINISHED |
| Object | port city of Salonika |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: port city of Salonika | Statement: [Salonika Expedition, basedAround, port city of Salonika]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basedAround Context triple: [Salonika Expedition, basedAround, port city of Salonika]
-
A.
around
Indicates that one entity is located or moves on all or most sides of another entity, encircling or surrounding it spatially.
-
B.
createdAround
Indicates that something was brought into existence or produced approximately at a particular time or within an imprecise time period.
-
C.
activeAround
Indicates that an entity is performing actions or exhibiting activity in the vicinity of another entity or location.
-
D.
developedAround
chosen
Indicates that one entity was created, designed, or evolved with the other entity as its central focus, basis, or surrounding context.
-
E.
areBasedOn
Indicates that one entity is founded, derived, or developed from the principles, content, or structure of another entity.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69b3451743608190808f41d17ccf2650 |
completed | March 12, 2026, 10:58 p.m. |
| NER | Named-entity recognition | batch_69b34e098da881909a0cc339cc186627 |
completed | March 12, 2026, 11:36 p.m. |
| PD | Predicate disambiguation | batch_69b347efd9b08190bb50f82e4e7fe06d |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:04 p.m.